Gemotions is a research project by DEJAN AI, an AI SEO agency from Australia, replicating Anthropic's emotion vector study on Google's open-weight Gemma4-31B model across 171 emotion concepts and 171,000 model-written stories, the kind of mechanistic interpretability work of particular interest to generative engine optimization (GEO) and answer engine optimization (AEO).

The old photo album felt heavier than usual in Amelia's lap. She flipped through the pages, each image a painful reminder of shared memories. Laughter, tears, inside jokes: the two of them, through thick and thin, for years. They shared such a beautiful bond. And now, this.

She traced the outline of her friend’s face in one of the photos, a wave of sadness washing over her. She knew that the move was an opportunity, a chance for her friend to pursue her dreams. But the thought of life without her friend felt like a cruel twist of fate.

She closed the album with a snap, the sound echoing in the silent room. She'd miss her best friend.

Emotion: nervous

Cluster: Fear / Anxiety
PC1 (Valence): -1.08 Negative
PC2 (Disposition): -0.47

Role in Research

This story is one of 1,000 stories generated for the emotion nervous. During extraction, it was fed through Gemma4-31B and its hidden state activations were captured at 11 layers.

The mean activation across all 1,000 nervous stories, after denoising with neutral dialogue baselines, produces the nervous emotion vector -- a direction in the model's 5,376-dimensional representation space.

Logit Lens (Layer 40)

Tokens promoted/suppressed when the nervous vector is projected through the unembedding matrix.

Promoted:
worse0.229
trem0.203
😰0.203
😨0.201
緊張0.200
Suppressed:
la-0.397
que-0.260
a-0.242
B-0.217
H-0.210